Google Open-Sources Tool That Watermarks AI-Generated Text

Developers can now embed and detect watermarks in their AI applications responsibly.

The spread of misinformation from AI-generated content on the internet has become a major issue over the past few years. Many attempts to detect AI-generated content have been made, but no tool yet exists with high accuracy. 

Even OpenAI discontinued its AI classifier, citing a low rate of accuracy in detecting AI and human-written texts.

We are working to incorporate feedback and are currently researching more effective provenance techniques for text, and have made a commitment to develop and deploy mechanisms that enable users to understand if audio or visual content is AI-generated. — OpenAI

Now, Google is addressing the misinformation challenge by open-sourcing its own tool, SynthID, a tool designed to detect AI-generated content.

For the rest of the article, we’ll cover the following topics:

• What is SynthID?

• How SynthID works

  • Applying watermark

  • Detecting watermark

• How and where to try SynthID

• Current limitations of SynthID

• Final thoughts

Let’s get started.